Kaiyang Zhou @kaiyangzhou Twitter profile

Last Seen Profiles

@stwmaniax

@cocoa_nol

@dana_brasel

@bokeplokalmalam

@FolkochForsvar

@BackToNormalUSA

@alyudur

@KCCrimeStop

@tresareed4

@sharfarazbd

@TimPCarver

@tanzenning

@Prasshmehta

@StackTeX

@Gianferreyra_

@Ami_Faku

@SeYDuNa_21

@Obake_Ya

@macro_dg

@o0oaeo0o

@KylieSpecht2025

@stwmaniax

@HaccsaS

@samsecrest72

@antsiro

@bokeplokalmalam

@mm5121187

@KichiMitsurugi

@YLIoro

@yoavgallant

@sepideh_tahanii

@tnk24612

@Brady_jpeg

@nephvishnoi

@ladelarosar

@onlee2468

Kaiyang Zhou

@kaiyangzhou

1 year

The slides and video recordings have been put on the tutorial website Happy prompting!

Ziwei Liu

@liuziwei7

1 year

#CVPR2023 Our "Prompting in Vision" Tutorial was a huge success. Thanks so much to our amazing speakers and all the participants! - The tutorial slides and recordings will be uploaded to our tutorial website:

4

55

223

1

26

130

Kaiyang Zhou

@kaiyangzhou

5 months

Looking for PhD/MPhil/RA to work together on cutting-edge research on foundation models (LLM, VLM, ...). Feel free to reach out via email if you are interested

7

9

116

Kaiyang Zhou

@kaiyangzhou

2 years

spent a long time trying to figure out why my neural network doesn't learn anything eventually found the values coming out from relu are zeros ... changed to leakyrelu and everything works just fine is there a good toolbox to use for debugging neural networks quickly?

5

9

110

Kaiyang Zhou

@kaiyangzhou

2 years

Our survey paper on domain generalization, titled "Domain Generalization: A Survey," has been accepted for publication at TPAMI, the flagship journal in AI! Paper:

Domain Generalization: A Survey

Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce. This is because most learning algorithms strongly rely on the...

arxiv.org

3

21

107

Kaiyang Zhou

@kaiyangzhou

1 year

We're organizing a tutorial on Prompting in Vision at #CVPR2023 w/ @liuziwei7 @phillip_isola @hyojinbahng @lschmidt3 @sarahmhpratt @denny_zhou Please visit our website at to know more about this event

0

30

105

Kaiyang Zhou

@kaiyangzhou

1 year

If you aim to pursue a PhD in #computervision , #machinelearning , and #AI , the Nvidia-HKBU Joint PhD Fellowship Scheme provided by our Dept would be a great program to join! Web: . Deadline: 31 October 2023/.

0

12

95

Kaiyang Zhou

@kaiyangzhou

2 years

If you're working on open-vocabulary detection, you might be interested in this #ECCV2022 work, which shows how the Transformer-based detector, DETR, is turned into an open-vocabulary detector using large vision-language models like CLIP.

AK

@_akhaliq

3 years

Open-Vocabulary DETR with Conditional Matching abs:

0

17

76

0

16

79

Kaiyang Zhou

@kaiyangzhou

2 years

NEWS: CoOp has been accepted to IJCV, the flagship journal in computer vision! The paper presents comprehensive studies of adapting large, pre-trained vision-language models like CLIP using *prompt learning* Have spare time when attending #ICML2022 ? Take a look at our paper :)

AK

@_akhaliq

3 years

Learning to Prompt for Vision-Language Models pdf: abs: a differentiable approach that focuses on continuous prompt learning to facilitate deployment of pre-trained vision language models in downstream datasets

2

26

120

0

13

58

Kaiyang Zhou

@kaiyangzhou

2 years

#ICLR2023 : "This year, we are introducing a new program for ACs to (virtually) meet and discuss with reviewers only for borderline cases ..." ICLR @iclr_conf has made a significant move towards building a better (fairer) community. Good for researchers choosing ICLR

1

7

56

Kaiyang Zhou

@kaiyangzhou

2 years

Honored to be invited to serve as Area Chair / Senior Program Committee Member for #BMVC2022 & #AAAI2023 Thanks! @TheBMVA @RealAAAI 🤗

8

0

50

Kaiyang Zhou

@kaiyangzhou

3 months

Looking for a good prompt? Join our workshop at #CVPR2024 on June 17! 🚀✨ @CVPR @_amirbar @liuziwei7 @YGandelsman @SharonYixuanLi @hyojinbahng @LINJIEFUN @amirgloberson @zhang_yuanhan @BoLi68567011 @JingkangY

0

10

49

Kaiyang Zhou

@kaiyangzhou

2 years

conditional prompt learning vision: - (CVPR'22) NLP: - (NAACL'22)

1

5

47

Kaiyang Zhou

@kaiyangzhou

2 years

Hi all, we're organizing an #IJCV special issue on The Promises and Dangers of Large Vision Models. w/ @liuziwei7 @XiaohuaZhai @ChunyuanLi @kate_saenko_ Please visit for more info.

1

7

41

Kaiyang Zhou

@kaiyangzhou

8 months

Excited to announce the launch of the Prompting in Vision workshop at #CVPR2024 ! More details at . Paper submission deadline: Mar 15, 2024.

0

12

37

Kaiyang Zhou

@kaiyangzhou

3 years

#CVPR2022 : Conditional Prompt Learning for Vision Language Models w/ @JingkangY @ccloy @liuziwei7 TL;DR: A simple conditional prompt learning approach that addresses the generalizability issue of static prompts paper: code:

2

7

37

Kaiyang Zhou

@kaiyangzhou

4 years

Interested in learning the field of #DomainGeneralization ? Check our recently released survey in this topic at , with coverage on the history, related fields, datasets, methodologies, potential directions, and so on. Joint work with @ccloy @liuziwei7

Domain Generalization: A Survey

Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce. This is because most learning algorithms strongly rely on the...

arxiv.org

1

8

29

Kaiyang Zhou

@kaiyangzhou

7 months

#CVPR2024 Please consider submitting your work to our workshop on Prompting in Vision (Track on Emerging Topics) More details at

#CVPR2024

@CVPR

8 months

The list of #CVPR2024 workshops is now available!

2

35

189

0

9

28

Kaiyang Zhou

@kaiyangzhou

2 years

Tired of seeing too many tweets talking about their papers getting accepted to #ECCV2022 ? (Congrats!) This one is different: I'm happy that 3/3 papers I gave weak accept & above are accepted to #ECCV2022 !

1

0

25

Kaiyang Zhou

@kaiyangzhou

1 year

If you’re at #IJCAI2023 in Macau and interested in prompt learning, pls come to Kokand 6307 where I will give a talk about prompting at 2pm 🤓

0

1

23

Kaiyang Zhou

@kaiyangzhou

3 years

@ak92501 Interesting work👏 Foundation models are becoming a trend! And adapting them to downstream applications with as low cost as possible is equally important! You might be interested to read our recent work on adapting CLIP-like models

Learning to Prompt for Vision-Language Models

Large pre-trained vision-language models like CLIP have shown great potential in learning representations that are transferable across a wide range of downstream tasks. Different from the...

arxiv.org

1

22

Kaiyang Zhou

@kaiyangzhou

11 months

The special issue has been published online at . If you'd like to have an overview of all accepted papers, you can read our Guest Editorial at . Big thanks to the guest editor team, reviewers, EICs and the editorial team at Springer!

Kaiyang Zhou

@kaiyangzhou

2 years

Hi all, we're organizing an #IJCV special issue on The Promises and Dangers of Large Vision Models. w/ @liuziwei7 @XiaohuaZhai @ChunyuanLi @kate_saenko_ Please visit for more info.

1

7

41

1

4

21

Kaiyang Zhou

@kaiyangzhou

2 years

This might be of interest to you if you're working on topics related to large-scale models, e.g., parameter-efficient downstream adaptation ...

GitHub - Computer-Vision-in-the-Wild/CVinW_Readings: A collection of papers on the topic of...

A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)'' - Computer-Vision-in-the-Wild/CVinW_Readings

github.com

0

7

19

Kaiyang Zhou

@kaiyangzhou

1 year

Our tutorial will start soon! @CVPR Please join us at West 223-224

Kaiyang Zhou

@kaiyangzhou

1 year

We're organizing a tutorial on Prompting in Vision at #CVPR2023 w/ @liuziwei7 @phillip_isola @hyojinbahng @lschmidt3 @sarahmhpratt @denny_zhou Please visit our website at to know more about this event

0

30

105

0

2

17

Kaiyang Zhou

@kaiyangzhou

2 years

Submitting a paper to TPAMI is like ...

1

0

16

Kaiyang Zhou

@kaiyangzhou

1 year

Thanks everyone!

Ziwei Liu

@liuziwei7

1 year

#CVPR2023 Our "Prompting in Vision" Tutorial was a huge success. Thanks so much to our amazing speakers and all the participants! - The tutorial slides and recordings will be uploaded to our tutorial website:

4

55

223

0

15

Kaiyang Zhou

@kaiyangzhou

2 years

#NeurIPS2022 Hmm, what's the best approach to make reviewers respond to your rebuttal?

1

2

15

Kaiyang Zhou

@kaiyangzhou

10 months

We have a paper to present at the conference: “what makes good examples for visual in-context learning?” If you’re interested in visual in-context learning, talk to @zhang_yuanhan

Yuanhan (John) Zhang

@zhang_yuanhan

10 months

I’ll be at #NeurIPS2023 from December 11th to 16th. Feel free to DM me if you’re interested in discussing multi-modal models, visual prompting, and related areas!

0

2

10

0

2

14

Kaiyang Zhou

@kaiyangzhou

1 year

@liuziwei7 @denny_zhou @liuziwei7 @denny_zhou @phillip_isola @hyojinbahng @lschmidt3 @sarahmhpratt Just uploaded some photos taken during the tutorials. Pls see . Will upload the slides and video recordings soon. Stay tuned!

1

11

Kaiyang Zhou

@kaiyangzhou

2 years

#CVPR2022 is approaching! Our paper, CoCoOp, shows conditional prompt learning is more (i) generalizable to wider unseen classes, (ii) transferable across problems/tasks, and (iii) robust to domain shift. paper: code:

1

14

Kaiyang Zhou

@kaiyangzhou

2 years

honored to receive the recognition :-)

European Conference on Computer Vision #ECCV2024

@eccvconf

2 years

List of #ECCV2022 Outstanding Reviewers. Thank you all for your service! 👏

5

4

55

0

14

Kaiyang Zhou

@kaiyangzhou

2 years

A great opportunity to learn the latest advances in using AI for solving healthcare problems #ArtificialIntelligence #MachineLearning #Healthcare

The AI Talks

@TheAITalksOrg

2 years

**Upcoming talk** Using AI to Diagnose and Assess Parkinson's Disease: Challenges, Algorithms, and Applications by @yang_yuzhe from MIT Join us via

1

5

11

0

3

13

Kaiyang Zhou

@kaiyangzhou

2 years

@ComputerSociety Congrats! Would like to promote our recently accepted survey at TPAMI, Domain Generalization: A Survey (), which gives a comprehensive summary of and an outlook for the emerging field of domain generalization, aka out-of-distribution generalization :-)

0

3

13

Kaiyang Zhou

@kaiyangzhou

2 years

#CVPR2022 papers are all out:

0

1

11

Kaiyang Zhou

@kaiyangzhou

2 years

Just submitted my PC (reviewer) nominations for #AAAI2023 Have seen/experienced low-quality reviews in the past (some even complained about "undergrad" reviewers who don't have publications) All reviewers I recommend are qualified. Together we make the community better

Kaiyang Zhou

@kaiyangzhou

2 years

Honored to be invited to serve as Area Chair / Senior Program Committee Member for #BMVC2022 & #AAAI2023 Thanks! @TheBMVA @RealAAAI 🤗

8

0

50

1

0

11

Kaiyang Zhou

@kaiyangzhou

2 years

JK is attending #ECCV2022 in person. Feel free to poke him if you’d like to know about our work

Jingkang Yang ✈️ECCV🇮🇹

@JingkangY

2 years

🥳 Attending my first-ever in-person computer vision conference #ECCV2022 ! Let's talk about scene understanding, OOD detection & generalization, and also prompt engineering in @eccvconf 🇮🇱

0

1

37

1

0

10

Kaiyang Zhou

@kaiyangzhou

7 months

The deadline for paper submission is approaching: **15 Mar 2024**. Join us if you are interested in the emerging prompting-based pardigm. @_amirbar @liuziwei7 @YGandelsman @SharonYixuanLi @hyojinbahng @LINJIEFUN @amirgloberson @zhang_yuanhan @BoLi68567011 @JingkangY

Kaiyang Zhou

@kaiyangzhou

7 months

#CVPR2024 Please consider submitting your work to our workshop on Prompting in Vision (Track on Emerging Topics) More details at

0

9

28

0

5

10

Kaiyang Zhou

@kaiyangzhou

2 years

A gentle reminder: the submission deadline is about a month away.

Kaiyang Zhou

@kaiyangzhou

2 years

Hi all, we're organizing an #IJCV special issue on The Promises and Dangers of Large Vision Models. w/ @liuziwei7 @XiaohuaZhai @ChunyuanLi @kate_saenko_ Please visit for more info.

1

7

41

0

2

10

Kaiyang Zhou

@kaiyangzhou

2 years

looking for object detectors that use fewer labeled examples and have the capability to leverage unlabeled data as well as to cope with long-tail data distributions? take a look at our recent paper published in IJCV this year (arxiv coming soon)

1

2

10

Kaiyang Zhou

@kaiyangzhou

3 years

Thanks @ak92501 . Tired of tuning prompts for vision-language models like CLIP? Why not use CoOp to learn prompts! It's both data-efficient and domain-generalizable😎 Joint work w/ @yangtafrog @ccloy @liuziwei7

Ziwei Liu

@liuziwei7

3 years

Thanks, @ak92501 . The main idea of CoOp is to model context in prompts using continuous representations and perform end-to-end learning from data. CoOp shows strong data-efficient learning capability as well as robustness to distribution shift. Code: .

1

4

27

0

9

Kaiyang Zhou

@kaiyangzhou

3 years

I really like this question from the #ICML2022 review form. Would be happy to see this in other CV/ML venues! #CVPR2022 #ECCV2022 #ICLR2022 ...

0

1

9

Kaiyang Zhou

@kaiyangzhou

2 years

Join us if you'd like to hear the latest progress in transfer learning, particularly robust fine-tuning

The AI Talks

@TheAITalksOrg

2 years

**Upcoming talk** Robust and accurate fine-tuning for large neural networks by Mitchell Wortsman from the University of Washington @Mitchnw Join us via

0

9

0

8

Kaiyang Zhou

@kaiyangzhou

2 years

Don’t miss it if you’re interested in AI Safety

The AI Talks

@TheAITalksOrg

2 years

Upcoming Talk: 𝕌𝕟𝕤𝕠𝕝𝕧𝕖𝕕 𝕄𝕃 𝕊𝕒𝕗𝕖𝕥𝕪 ℙ𝕣𝕠𝕓𝕝𝕖𝕞𝕤 by @DanHendrycks Join us via

0

6

14

0

1

8

Kaiyang Zhou

@kaiyangzhou

2 years

Interesting to see that our MixStyle method () has recently been applied to analyzing remote sensing images (), audio data (), and medical images (). #MachineLearning

2

1

8

Kaiyang Zhou

@kaiyangzhou

4 years

Our paper, "Domain Generalization with MixStyle", got acccepted to #ICLR2021 . The idea is simple: we mix the instance-level CNN style statistics between samples. Openreview:

0

1

7

Kaiyang Zhou

@kaiyangzhou

2 years

@GoogleAI Very interesting and inspiring work! Would like to share (i.e. self-promote) a relevant work of ours: "Learning to Prompt for Vision-Language Models" (), which shows that prompt learning works very well for adapting CLIP-like vision foundation models

Learning to Prompt for Vision-Language Models

Large pre-trained vision-language models like CLIP have shown great potential in learning representations that are transferable across a wide range of downstream tasks. Different from the...

arxiv.org

0

2

7

Kaiyang Zhou

@kaiyangzhou

10 months

Embodied AI is a trendy topic. Don't miss the talk!

The AI Talks

@TheAITalksOrg

10 months

𝗨𝗽𝗰𝗼𝗺𝗶𝗻𝗴 𝗧𝗮𝗹𝗸 Generalist Embodied AI in an Open World by Xiaojian Ma @jeasinema from Beijing Institute for General Artificial Intelligence (BIGAI). Join us via

0

4

10

0

7

Kaiyang Zhou

@kaiyangzhou

2 years

Prof. Ge will visit our lab on Friday so this will be the very first on-site talk in The AI Talks series

The AI Talks

@TheAITalksOrg

2 years

**Upcoming talk (on-site)** MMAI: Close the loop for Medical AI application by Prof. Zongyuan Ge from Monash University @MonasheResearch Join us via

0

1

7

0

7

Kaiyang Zhou

@kaiyangzhou

1 year

#PHD #HKPFS #AI #MachineLearning #ComputerVision Call for HKPFS 2024/25 application

1

2

7

Kaiyang Zhou

@kaiyangzhou

3 years

@ylzou_Zack Agreed! Adapting large vision foundation models (w prompt learning) is critical and becoming a trend Not aware of any talks, but the following works might be of interest to you - : adapt CLIP to downstream image recognition

2

0

7

Kaiyang Zhou

@kaiyangzhou

5 months

Clarification: I'm looking for students to join my group as PhD/MPhil/RA. Not seeking collaboration.

0

7

Kaiyang Zhou

@kaiyangzhou

2 years

@eccvconf @JingkangY

0

6

Kaiyang Zhou

@kaiyangzhou

2 years

A collection of papers applying prompt tuning to open-vocab object detection: - DetPro (CVPR'22): - DenseCLIP (CVPR'22): - PromptDet:

1

6

Kaiyang Zhou

@kaiyangzhou

7 months

1st ai talk in 2024! interested in knowing the recent trendy work, InstantID? join us!

The AI Talks

@TheAITalksOrg

7 months

【THE AI TALKS】InstantID: Zero-shot Identity-Preserving Generation in Seconds Join us via More info:

2

10

32

0

6

Kaiyang Zhou

@kaiyangzhou

2 years

Just landed in Mastodon. The world seems cleaner there :P

Kaiyang Zhou (@[email protected])

1 Post, 2 Following, 3 Followers · Postdoc at NTU. Interested in AI, machine learning, deep learning, and computer vision.

sigmoid.social

0

6

Kaiyang Zhou

@kaiyangzhou

2 years

In case you're looking for a job/internship

Bo Dai

@doubledaibo

2 years

Luckily 6/8 #ECCV2022 accepted submissions. Most of them are rejected once, with good suggestions to help improve our papers. Thanks to our reviewers and more importantly my students and collaborators for their hard work! Ps: I'm looking for interns and researchers to join us :)

2

0

52

2

0

6

Kaiyang Zhou

@kaiyangzhou

2 years

Papers will be processed soon after submission.

Ziwei Liu

@liuziwei7

2 years

#IJCV We are eager to see your exciting works submitted to our IJCV Special Issue "The Promises and Dangers of Large Vision Models" @SpringerNature

0

2

11

1

0

6

Kaiyang Zhou

@kaiyangzhou

2 years

The submission system has been set up When submitting a paper to this SI, please select the "S.I.: The Promises and Dangers of Large Vision Models" article type

Kaiyang Zhou

@kaiyangzhou

2 years

Hi all, we're organizing an #IJCV special issue on The Promises and Dangers of Large Vision Models. w/ @liuziwei7 @XiaohuaZhai @ChunyuanLi @kate_saenko_ Please visit for more info.

1

7

41

0

2

6

Kaiyang Zhou

@kaiyangzhou

2 years

looking for generalizable, off-the-shelf human features? try our OSNet or OSNet-AIN (ICCV'19, TPAMI'21), which was originally developed for person re-id but has since been proven effective beyond re-id model zoo: see below for some use cases:

1

0

5

Kaiyang Zhou

@kaiyangzhou

11 months

"MixStyle Neural Networks for Domain Generalization and Adaptation" (published in IJCV 2023) a more comprehensive study of our previously proposed MixStyle approach—a simple plug-and-play module for domain generalization and adaptation pdf:

0

6

Kaiyang Zhou

@kaiyangzhou

2 years

an interesting topic that is worth a visit!

Chaowei Xiao

@ChaoweiX

2 years

We will host the #ICLR2022 Workshop on Socially Responsible Machine Learning on Friday at 9:20 AM EDT. A line of outstanding speakers will discuss emerging topics on machine learning #security , #fairness , #ethics and #privacy . Workshop website:

0

20

91

0

6

Kaiyang Zhou

@kaiyangzhou

2 years

not sure if you've noticed the bunny bot, which also appeared in the Talks's new year poster it was synthesized by a generative AI! please subscribe to the newsletter to join our talks and interact with world-leading experts in AI suggestions are also welcome

Jingkang Yang ✈️ECCV🇮🇹

@JingkangY

2 years

Check out the recording of @RinonGal 's talk on personalizing your image with the #DIFFUSION model Stay tuned for @DrJimFan 's talk on 16 Feb (Thur) :D Don't forget to subscribe from for zoom link!

0

2

4

0

5

Kaiyang Zhou

@kaiyangzhou

2 years

Have spare time while attending #CVPR2022 ? Would like to recommend our survey paper on the topic of domain generalization, which discusses a wide spectrum of methods for improving generalization of deep neural networks

Kaiyang Zhou

@kaiyangzhou

4 years

Interested in learning the field of #DomainGeneralization ? Check our recently released survey in this topic at , with coverage on the history, related fields, datasets, methodologies, potential directions, and so on. Joint work with @ccloy @liuziwei7

1

8

29

0

1

5

Kaiyang Zhou

@kaiyangzhou

2 years

very excited to learn this news as a native Hokkien speaker myself

Jia-Bin Huang

@jbhuang0604

2 years

This is AMAZING! So cool to see that everyone would be able to communicate with people speaking (Taiwanese) Hokkien!

0

2

15

0

5

Kaiyang Zhou

@kaiyangzhou

3 years

We indeed failed to "cherry-pick" examples that make sense😂 As discussed in the paper, using nearest words for interpretation might be misleading as the found words are still distant from the learned vectors and nearby vectors do not necessarily have the same meaning

Jingkang Yang ✈️ECCV🇮🇹

@JingkangY

3 years

Learnable Prompt Engineering for CLIP Interestingly, the optimized prompts look weird but do help general performance and generalizability lol

1

0

5

Kaiyang Zhou

@kaiyangzhou

3 years

looking for a simple, efficient, plug-and-play module to improve your CNNs' generalization? try MixStyle, a param-free layer proved effective on domain generalization and adaptation paper: code: #machinelearning #computervision

1

0

5

Kaiyang Zhou

@kaiyangzhou

1 year

Please join the talk if you are interested in natural language processing and text2image generation

The AI Talks

@TheAITalksOrg

1 year

𝗨𝗽𝗰𝗼𝗺𝗶𝗻𝗴 𝗧𝗮𝗹𝗸 Collecting and Leveraging Data without Crowd Workers by Yuval Kirstain @YKirstain from Tel Aviv University Join us via

0

4

11

0

4

Kaiyang Zhou

@kaiyangzhou

2 years

Just opened an account on Zhihu: If you're also on Zhihu, let's connect! :)

0

4

Kaiyang Zhou

@kaiyangzhou

3 years

👏👏👏

MMLab@NTU

@MMLabNTU

3 years

Congrats to our team members Kelvin Chan @kelvinckchan , Chongyi Li @LiChongyi , Liang Pan @LiangPan4 , Jingkang Yang @yangtafrog , and Kaiyang Zhou @kaiyangzhou 🎉🎉🎉

1

10

1

0

4

Kaiyang Zhou

@kaiyangzhou

2 years

Some updates: Adds an "Evaluation" subsection; Includes more datasets in Tab.1 (w/ categorization based on applications); Discusses test-time training (related topic), RL methods (Sec.3.8), theories (Sec.4) & more recent work; etc. A relevant codebase:

GitHub - KaiyangZhou/Dassl.pytorch: A PyTorch toolbox for domain generalization, domain adaptation...

A PyTorch toolbox for domain generalization, domain adaptation and semi-supervised learning. - KaiyangZhou/Dassl.pytorch

github.com

Kaiyang Zhou

@kaiyangzhou

4 years

Interested in learning the field of #DomainGeneralization ? Check our recently released survey in this topic at , with coverage on the history, related fields, datasets, methodologies, potential directions, and so on. Joint work with @ccloy @liuziwei7

1

8

29

0

4

Kaiyang Zhou

@kaiyangzhou

2 years

please check out today's talk if you're interested in distribution shifts the Talks will resume next year!

The AI Talks

@TheAITalksOrg

2 years

here is the video recording:

0

2

0

3

Kaiyang Zhou

@kaiyangzhou

2 years

cool, and inspiring

0

1

4

Kaiyang Zhou

@kaiyangzhou

1 year

Don’t miss the talk!

The AI Talks

@TheAITalksOrg

1 year

𝗨𝗽𝗰𝗼𝗺𝗶𝗻𝗴 𝗧𝗮𝗹𝗸 Multimodal Representation Learning with Deep Generative Models by Shweta Mahajan @Matewhs from University of British Columbia Join us via

0

5

15

0

4

Kaiyang Zhou

@kaiyangzhou

2 years

Also worth mentioning that, a concurrent work shows conditional prompt learning is also effective in the #NLP domain Check this #NAACL2022 paper out:

IDPG: An Instance-Dependent Prompt Generation Method

Prompt tuning is a new, efficient NLP transfer learning paradigm that adds a task-specific prompt in each input instance during the model training stage. It freezes the pre-trained language model...

arxiv.org

Kaiyang Zhou

@kaiyangzhou

2 years

#CVPR2022 is approaching! Our paper, CoCoOp, shows conditional prompt learning is more (i) generalizable to wider unseen classes, (ii) transferable across problems/tasks, and (iii) robust to domain shift. paper: code:

1

14

1

0

4

Kaiyang Zhou

@kaiyangzhou

2 years

a paper isn't judged by three individuals but the whole community

Yi Ma

@YiMaTweets

2 years

I always tell all my students: do not take outcome of *any* conferences seriously, no matter what others tell you. Focus on doing significant research and writing good papers. Treat conference submissions as a drill for sharpening your academic skills - that is all what they are

5

45

473

0

3

Kaiyang Zhou

@kaiyangzhou

2 years

I'm extremely honored to work with four established researchers, and together, I believe we can provide the community with a timely collection of research addressing the emerging issues in LVMs Also thank @kmoretticompsci for the help :-)

1

3

Kaiyang Zhou

@kaiyangzhou

4 months

@GoogleDeepMind Cool, but in Hong Kong we drive on the left of the road

0

3

Kaiyang Zhou

@kaiyangzhou

2 years

Interesting to see MixStyle also works for processing point clouds

Kaiyang Zhou

@kaiyangzhou

2 years

Interesting to see that our MixStyle method () has recently been applied to analyzing remote sensing images (), audio data (), and medical images (). #MachineLearning

2

1

8

0

1

3

Kaiyang Zhou

@kaiyangzhou

2 years

In case you didn't notice, our website paid tribute to the PSG Football Club 🫡

PSG.FR - Paris Saint-Germain official website

Paris Saint-Germain official website : news, fixtures and results, player profiles, videos, photos, transfers, live match coverages, highlights, tickets, online shop.

en.psg.fr

AK

@_akhaliq

2 years

Panoptic Scene Graph Generation abs: project page: github:

0

36

148

0

3

Kaiyang Zhou

@kaiyangzhou

2 years

A great opportunity! Do not hesitate to contact Da.

Da Li

@dali_academic

2 years

We SAIC Cambridge still have multiple internships available for 2022 (official link stays tuned) for possibly working on one/more of the following topics, -Self-supervision, -AutoML, -Multi-modal, -Federated Learning. Please reach me if you or anyone you know have any interest.

2

3

10

0

3

Kaiyang Zhou

@kaiyangzhou

2 years

@3scorciav @TheBMVA @RealAAAI Hi Victor, also heard your name while I was in Samsung. I haven't thought about whether to attend but certainly miss London a lot! Will see.

0

2

Kaiyang Zhou

@kaiyangzhou

2 years

Don't miss out if you're at #ECCV2022

0

2

Kaiyang Zhou

@kaiyangzhou

3 years

"the simpler models seemed to fare better on the corrected data than the more complicated models ... In other words, we may have an inflated sense of how great these complicated models are because of flawed testing data"

MIT Technology Review

@techreview

3 years

The 10 most cited AI data sets are riddled with errors.

0

21

51

0

2

Kaiyang Zhou

@kaiyangzhou

2 years

@CSProfKGD "knowing someone is (sometimes) better than knowing something"

0

2

Kaiyang Zhou

@kaiyangzhou

1 year

very helpful

Xiaoguang Han

@XiaogHan

1 year

We maintained a webpage, "CV-Highlight-Papers", which contains all Oral ("Highlight" at CVPR 2023) papers in CVPR/ICCV/ECCV/NeurIPS/ICLR from 2017 to now. And each paper owns github link, project page link, stars and citations. Hope it can help.

1

19

119

0

1

2

Kaiyang Zhou

@kaiyangzhou

2 years

The paper illustrates the problem definition, discusses the history, relates the problem to neighboring fields like domain adaptation and transfer learning, ...

1

0

1

Kaiyang Zhou

@kaiyangzhou

6 years

@OpenAI Hi, is there a way to subscribe to the blog update on ? (notification by email I mean)

0

1

Kaiyang Zhou

@kaiyangzhou

2 years

@CalcCon @MarcJSchmidt elegant!

0

1

Kaiyang Zhou

@kaiyangzhou

2 years

@Jacob292020 @Yezhou_Yang @ApgAsu @liuhuan @cbaral Congrats! Dr. Fang

1

0

1

Kaiyang Zhou

@kaiyangzhou

2 years

free pdf:

0

1

Kaiyang Zhou

@kaiyangzhou

2 months

@yang_yuzhe @UCLA @CompMedUCLA @CS_UCLA @UCLAengineering @UCLAComSci @dgsomucla @UCLAHealth @MIT_CSAIL @AIHealthMIT Congrats!

0

1

Kaiyang Zhou

@kaiyangzhou

2 years

@TheAITalksOrg @ShuaiYang1991 @MMLabNTU If you're interested in style transfer and image editing, please join the talk and interact with our speaker. Dr. Yang will "demystify" his recent work, VToonify, which has caused a sensation on social media (meaning that the community loves it!)

Shuai Yang

@ShuaiYang1991

2 years

Combine #stableDifusion with style transfer models #VToonify and #DualStyleGAN . Toonify videos using #VToonify with the backbone #DualStyleGAN trained on face images generated by #stableDifusion . (1/5) #aiartist #deeplearning

10

207

1K

0

1

Kaiyang Zhou

@kaiyangzhou

2 years

@jperezrua oops, sorry to hear that

0

1

Kaiyang Zhou

@kaiyangzhou

6 years

@louis_sherren hi, the centers are updated along with the model param, please check the train() func. pls ask directly on github next time cause i don't usually check twitter :)

0

1

Kaiyang Zhou

@kaiyangzhou

2 years

@YapengTian @bypark___ bad luck, perhaps other papers in the same batch have higher scores and the AC has to throw away some in order to keep the overall acceptance rate within a certain range, just a guess not sure if ACs were asked to maintain a certain acceptance rate

0

1

Kaiyang Zhou

@kaiyangzhou

7 months

@zhoubolei Congrats!

0

1

Kaiyang Zhou

@kaiyangzhou

8 months

@ziqi_huang_ @liuziwei7 @MMLabNTU Congrats and well deserved!

0

1

Kaiyang Zhou

@kaiyangzhou

2 years

gives a comprehensive survey on methods developed in the last decade (with an intuitive & concrete categorization), and also points out promising directions for future work.

1

0

1

Kaiyang Zhou

@kaiyangzhou

1 year

@muzairkhattak @mmaaz60 @hanoonaRasheed @KhanSalmanH @FahadShahbazkh3 @CVPR Keep prompting Muhammad :-)

1

0

1

Kaiyang Zhou

@kaiyangzhou

4 years

Interesting article on deep learning (Transformers) from an investor perspective

ARK Invest

@ARKInvest

4 years

"Transformers is a new architecture that enables computers to understand language with unprecedented accuracy. Unlike prior language models that processed words sequentially, Transformers can discern connections between and among words in a sentence." 📄:

8

45

291

0

1

Kaiyang Zhou

@kaiyangzhou

3 years

@ylzou_Zack - : prompt learning for videos - : prompt learning for domain adaptation

Domain Adaptation via Prompt Learning

Unsupervised domain adaption (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given. Current UDA approaches learn...

arxiv.org

0

1